Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Extended Reality Intelligence for Monitoring and Predicting Patient Readmission Risks

Martin Sanchez, Nick Tran, Vuthea Chheang

Abstract

Hospital readmissions remain a challenge for healthcare systems, especially among patients with chronic conditions such as diabetes. Unplanned readmissions within 30 days are costly, strain hospital resources, and can indicate poor care coordination or discharge planning. In this work, we explore the use of machine learning to predict readmission risk for diabetic inpatients and propose a mixed reality (MR) to provide effective visualization and insights. We trained an XGBoost classifier after data cleaning, encoding, and feature engineering. The model achieved an Area Under the Receiver Operating characteristic Curve (AUROC) of 0.72 and an Area Under the Precision-Recall Curve (AUPRC) of 0.11. Key predictive factors included prior inpatient visits, discharge disposition, and glycemic control indicators such as A1C (blood sugar test) results and medication adjustments. Additionally, we developed an MR prototype that visualize patient records and predictions containing risk level, major contributing factors, and a concise summary of care. Together, the predictive model and the MR interface aim to improve clinician awareness and communication around readmission risk in real-time clinical settings.

Towards Extended Reality Intelligence for Monitoring and Predicting Patient Readmission Risks

Abstract

Hospital readmissions remain a challenge for healthcare systems, especially among patients with chronic conditions such as diabetes. Unplanned readmissions within 30 days are costly, strain hospital resources, and can indicate poor care coordination or discharge planning. In this work, we explore the use of machine learning to predict readmission risk for diabetic inpatients and propose a mixed reality (MR) to provide effective visualization and insights. We trained an XGBoost classifier after data cleaning, encoding, and feature engineering. The model achieved an Area Under the Receiver Operating characteristic Curve (AUROC) of 0.72 and an Area Under the Precision-Recall Curve (AUPRC) of 0.11. Key predictive factors included prior inpatient visits, discharge disposition, and glycemic control indicators such as A1C (blood sugar test) results and medication adjustments. Additionally, we developed an MR prototype that visualize patient records and predictions containing risk level, major contributing factors, and a concise summary of care. Together, the predictive model and the MR interface aim to improve clinician awareness and communication around readmission risk in real-time clinical settings.
Paper Structure (15 sections, 4 figures, 1 table)

This paper contains 15 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Dataset
  4. Data Preprocessing
  5. Model Selection
  6. Model training
  7. Evaluation Metrics
  8. Mixed Reality (MR) Implementation
  9. Analysis and Results
  10. Exploratory Data Analysis
  11. Model Performance
  12. Feature Importance
  13. Extended Reality Intelligence
  14. Discussion
  15. Conclusion

Figures (4)

  • Figure 1: Readmission rate by number of prior inpatient visits. Patients with $\geq$3 prior visits had nearly triple the readmission risk.
  • Figure 2: Length of stay (LOS) vs. readmission status. Readmitted patients had longer median stays, indicating higher illness severity.
  • Figure 3: Results of discharge disposition and model performance: (a) Readmission rate by discharge disposition -- patients discharged to rehab or AMA had the highest risk and (b) receiver operating characteristic (ROC) and precision--recall (PR) curves for the XGBoost classifier. AUROC = 0.72, AUPRC = 0.11.
  • Figure 4: A "PatientCard" XR interface showing readmission risk and top predictive factors.